What is he best known for?
The fields of study he is best known for:
- Artificial intelligence
- Machine learning
- The Internet
Xia Hu mainly investigates Artificial intelligence, Social media, Machine learning, World Wide Web and Data science.
His Artificial intelligence research is multidisciplinary, incorporating elements of Structure and Natural language processing.
His research in the fields of Microblogging overlaps with other disciplines such as Semantic analytics.
His Machine learning study integrates concerns from other disciplines, such as Node and Embedding.
In general World Wide Web, his work in Social network is often linked to Consistency linking many areas of study.
His research in Deep learning intersects with topics in Collaborative filtering, Perceptron and Leverage.
His most cited work include:
- Neural Collaborative Filtering (1578 citations)
- Exploring temporal effects for location recommendation on location-based social networks (366 citations)
- Exploiting social relations for sentiment analysis in microblogging (297 citations)
What are the main themes of his work throughout his whole career to date?
His main research concerns Artificial intelligence, Machine learning, Social media, Recommender system and Theoretical computer science.
His Pattern recognition research extends to Artificial intelligence, which is thematically connected.
His work on Feature selection, Reinforcement learning and Feature learning as part of general Machine learning study is frequently connected to Generalization, therefore bridging the gap between diverse disciplines of science and establishing a new relationship between them.
The various areas that Xia Hu examines in his Social media study include Data science, Internet privacy and Social network.
Xia Hu interconnects Key and Leverage in the investigation of issues within Recommender system.
Node is closely connected to Embedding in his research, which is encompassed under the umbrella topic of Theoretical computer science.
He most often published in these fields:
- Artificial intelligence (46.75%)
- Machine learning (32.90%)
- Social media (23.81%)
What were the highlights of his more recent work (between 2019-2021)?
- Artificial intelligence (46.75%)
- Machine learning (32.90%)
- Theoretical computer science (10.39%)
In recent papers he was focusing on the following fields of study:
The scientist’s investigation covers issues in Artificial intelligence, Machine learning, Theoretical computer science, Reinforcement learning and Anomaly detection.
His study in the field of Deep learning, Interpretability and Feature is also linked to topics like Domain.
His Machine learning research is multidisciplinary, incorporating perspectives in Training set and Benchmark.
His Theoretical computer science study combines topics from a wide range of disciplines, such as Node, Embedding and Graph neural networks, Graph.
His research in Artificial neural network focuses on subjects like Topology, which are connected to Perspective.
His Recommender system study incorporates themes from Leverage and Hyperparameter.
Between 2019 and 2021, his most popular works were:
- Score-CAM: Score-Weighted Visual Explanations for Convolutional Neural Networks (42 citations)
- Fairness in Deep Learning: A Computational Perspective (20 citations)
- An Embarrassingly Simple Approach for Trojan Attack in Deep Neural Networks (16 citations)
In his most recent research, the most cited papers focused on:
- Artificial intelligence
- Machine learning
- The Internet
His primary areas of study are Artificial intelligence, Machine learning, Reinforcement learning, Embedding and Theoretical computer science.
His work in the fields of Artificial intelligence, such as Deep learning, Interpretability and Convolutional neural network, overlaps with other areas such as Pipeline and Class.
In the field of Machine learning, his study on Artificial neural network and Feature learning overlaps with subjects such as Generalization.
His Reinforcement learning research includes elements of Dual, Human–computer interaction, Collaborative learning, Key and Function approximation.
His biological study spans a wide range of topics, including Social influence and Normalization.
His work in Theoretical computer science covers topics such as Node which are related to areas like Hash function, Discrete optimization, Recommender system and Message passing.
This overview was generated by a machine learning system which analysed the scientist’s
body of work. If you have any feedback, you can
contact us
here.
